Mercurial > octave-nkf
view scripts/io/textread.m @ 17338:1c89599167a6
maint: End m-files with 1 blank line.
Simplifies automated grammarchecking script.
* scripts/@ftp/ascii.m, scripts/@ftp/binary.m, scripts/@ftp/cd.m,
scripts/@ftp/close.m, scripts/@ftp/delete.m, scripts/@ftp/dir.m,
scripts/@ftp/display.m, scripts/@ftp/ftp.m, scripts/@ftp/loadobj.m,
scripts/@ftp/mget.m, scripts/@ftp/mkdir.m, scripts/@ftp/mput.m,
scripts/@ftp/rename.m, scripts/@ftp/rmdir.m, scripts/@ftp/saveobj.m,
scripts/audio/lin2mu.m, scripts/audio/loadaudio.m, scripts/audio/mu2lin.m,
scripts/audio/record.m, scripts/audio/saveaudio.m, scripts/audio/setaudio.m,
scripts/deprecated/__error_text__.m, scripts/deprecated/cut.m,
scripts/deprecated/error_text.m, scripts/deprecated/isstr.m,
scripts/deprecated/polyderiv.m, scripts/deprecated/studentize.m,
scripts/deprecated/sylvester_matrix.m, scripts/general/bicubic.m,
scripts/general/celldisp.m, scripts/general/colon.m,
scripts/general/cplxpair.m, scripts/general/del2.m, scripts/general/display.m,
scripts/general/isdir.m, scripts/general/isequaln.m, scripts/general/loadobj.m,
scripts/general/private/__isequal__.m, scripts/general/private/__splinen__.m,
scripts/general/profexplore.m, scripts/general/quadgk.m,
scripts/general/randi.m, scripts/general/repmat.m, scripts/general/saveobj.m,
scripts/geometry/delaunay.m, scripts/help/__unimplemented__.m,
scripts/help/doc_cache_create.m, scripts/help/get_first_help_sentence.m,
scripts/help/help.m, scripts/help/print_usage.m,
scripts/help/private/__additional_help_message__.m,
scripts/help/private/__strip_html_tags__.m, scripts/help/type.m,
scripts/image/imfinfo.m, scripts/image/imformats.m, scripts/image/imread.m,
scripts/image/imwrite.m, scripts/image/private/__imfinfo__.m,
scripts/image/private/__imread__.m, scripts/image/private/__imwrite__.m,
scripts/image/private/imageIO.m, scripts/image/private/imwrite_filename.m,
scripts/image/private/ind2x.m, scripts/io/beep.m, scripts/io/strread.m,
scripts/io/textread.m, scripts/io/textscan.m, scripts/linear-algebra/krylov.m,
scripts/linear-algebra/subspace.m, scripts/miscellaneous/bug_report.m,
scripts/miscellaneous/bunzip2.m, scripts/miscellaneous/cast.m,
scripts/miscellaneous/copyfile.m, scripts/miscellaneous/debug.m,
scripts/miscellaneous/dir.m, scripts/miscellaneous/dump_prefs.m,
scripts/miscellaneous/error_ids.m, scripts/miscellaneous/fileattrib.m,
scripts/miscellaneous/gunzip.m, scripts/miscellaneous/isdeployed.m,
scripts/miscellaneous/ismac.m, scripts/miscellaneous/mex.m,
scripts/miscellaneous/mexext.m, scripts/miscellaneous/mkoctfile.m,
scripts/miscellaneous/movefile.m, scripts/miscellaneous/namelengthmax.m,
scripts/miscellaneous/news.m, scripts/miscellaneous/pack.m,
scripts/miscellaneous/perl.m,
scripts/miscellaneous/private/display_info_file.m,
scripts/miscellaneous/python.m, scripts/miscellaneous/rmappdata.m,
scripts/miscellaneous/run.m, scripts/miscellaneous/tar.m,
scripts/miscellaneous/tempname.m, scripts/miscellaneous/untar.m,
scripts/miscellaneous/unzip.m, scripts/miscellaneous/what.m,
scripts/miscellaneous/zip.m, scripts/optimization/fminunc.m,
scripts/optimization/fsolve.m, scripts/optimization/fzero.m,
scripts/optimization/glpk.m, scripts/optimization/optimget.m,
scripts/optimization/optimset.m, scripts/optimization/qp.m,
scripts/optimization/sqp.m, scripts/path/pathdef.m, scripts/pkg/pkg.m,
scripts/pkg/private/build.m, scripts/pkg/private/describe.m,
scripts/pkg/private/dirempty.m, scripts/pkg/private/get_forge_download.m,
scripts/pkg/private/get_forge_pkg.m,
scripts/pkg/private/get_unsatisfied_deps.m, scripts/pkg/private/install.m,
scripts/pkg/private/is_architecture_dependent.m,
scripts/pkg/private/list_forge_packages.m, scripts/pkg/private/rebuild.m,
scripts/pkg/private/shell.m, scripts/pkg/private/uninstall.m,
scripts/plot/axes.m, scripts/plot/box.m, scripts/plot/closereq.m,
scripts/plot/diffuse.m, scripts/plot/ezpolar.m, scripts/plot/findfigs.m,
scripts/plot/gco.m, scripts/plot/guidata.m, scripts/plot/guihandles.m,
scripts/plot/hdl2struct.m, scripts/plot/linkprop.m, scripts/plot/peaks.m,
scripts/plot/print.m, scripts/plot/private/__add_datasource__.m,
scripts/plot/private/__axis_label__.m, scripts/plot/private/__clabel__.m,
scripts/plot/private/__color_str_rgb__.m, scripts/plot/private/__contour__.m,
scripts/plot/private/__default_plot_options__.m,
scripts/plot/private/__errcomm__.m, scripts/plot/private/__file_filter__.m,
scripts/plot/private/__fltk_file_filter__.m,
scripts/plot/private/__getlegenddata__.m,
scripts/plot/private/__gnuplot_open_stream__.m,
scripts/plot/private/__gnuplot_print__.m,
scripts/plot/private/__go_draw_axes__.m,
scripts/plot/private/__interp_cube__.m, scripts/plot/private/__is_function__.m,
scripts/plot/private/__line__.m, scripts/plot/private/__marching_cube__.m,
scripts/plot/private/__next_line_style__.m, scripts/plot/private/__patch__.m,
scripts/plot/private/__pie__.m, scripts/plot/private/__pltopt__.m,
scripts/plot/private/__quiver__.m, scripts/plot/private/__scatter__.m,
scripts/plot/private/__stem__.m, scripts/plot/private/__uigetdir_fltk__.m,
scripts/plot/private/__uigetfile_fltk__.m,
scripts/plot/private/__uiobject_split_args__.m,
scripts/plot/private/__uiputfile_fltk__.m, scripts/plot/refresh.m,
scripts/plot/saveas.m, scripts/plot/shg.m, scripts/plot/specular.m,
scripts/plot/sphere.m, scripts/plot/struct2hdl.m, scripts/plot/subplot.m,
scripts/plot/uicontextmenu.m, scripts/plot/uicontrol.m, scripts/plot/uipanel.m,
scripts/plot/uipushtool.m, scripts/plot/uiresume.m,
scripts/plot/uitoggletool.m, scripts/plot/uitoolbar.m, scripts/plot/uiwait.m,
scripts/plot/waitforbuttonpress.m, scripts/polynomial/pchip.m,
scripts/polynomial/polyeig.m, scripts/polynomial/ppval.m,
scripts/prefs/addpref.m, scripts/prefs/getpref.m, scripts/prefs/ispref.m,
scripts/prefs/private/loadprefs.m, scripts/prefs/private/prefsfile.m,
scripts/prefs/private/saveprefs.m, scripts/prefs/setpref.m,
scripts/set/private/validargs.m, scripts/set/unique.m,
scripts/signal/arch_fit.m, scripts/signal/arch_rnd.m,
scripts/signal/arch_test.m, scripts/signal/arma_rnd.m,
scripts/signal/durbinlevinson.m, scripts/signal/fractdiff.m,
scripts/signal/freqz.m, scripts/signal/freqz_plot.m, scripts/signal/hurst.m,
scripts/signal/periodogram.m, scripts/signal/private/rectangle_lw.m,
scripts/signal/private/rectangle_sw.m, scripts/signal/private/triangle_sw.m,
scripts/signal/spectral_adf.m, scripts/signal/spectral_xdf.m,
scripts/signal/stft.m, scripts/signal/synthesis.m, scripts/signal/yulewalker.m,
scripts/sparse/colperm.m, scripts/sparse/eigs.m, scripts/sparse/etreeplot.m,
scripts/sparse/gmres.m, scripts/sparse/private/__sprand_impl__.m,
scripts/sparse/spdiags.m, scripts/sparse/sprandn.m, scripts/specfun/bessel.m,
scripts/specfun/betaln.m, scripts/specfun/expint.m,
scripts/special-matrix/gallery.m, scripts/startup/__finish__.m,
scripts/statistics/base/qqplot.m, scripts/statistics/distributions/tcdf.m,
scripts/statistics/distributions/wienrnd.m,
scripts/statistics/models/logistic_regression.m,
scripts/statistics/models/private/logistic_regression_derivatives.m,
scripts/statistics/models/private/logistic_regression_likelihood.m,
scripts/statistics/tests/anova.m, scripts/statistics/tests/bartlett_test.m,
scripts/statistics/tests/chisquare_test_homogeneity.m,
scripts/statistics/tests/chisquare_test_independence.m,
scripts/statistics/tests/cor_test.m,
scripts/statistics/tests/f_test_regression.m,
scripts/statistics/tests/hotelling_test.m,
scripts/statistics/tests/hotelling_test_2.m,
scripts/statistics/tests/kolmogorov_smirnov_test_2.m,
scripts/statistics/tests/kruskal_wallis_test.m,
scripts/statistics/tests/manova.m, scripts/statistics/tests/mcnemar_test.m,
scripts/statistics/tests/prop_test_2.m, scripts/statistics/tests/run_test.m,
scripts/statistics/tests/sign_test.m, scripts/statistics/tests/t_test.m,
scripts/statistics/tests/t_test_2.m,
scripts/statistics/tests/t_test_regression.m,
scripts/statistics/tests/u_test.m, scripts/statistics/tests/var_test.m,
scripts/statistics/tests/welch_test.m,
scripts/statistics/tests/wilcoxon_test.m, scripts/statistics/tests/z_test.m,
scripts/statistics/tests/z_test_2.m, scripts/strings/strcat.m,
scripts/strings/strjoin.m, scripts/strings/strsplit.m,
scripts/testfun/__have_feature__.m, scripts/testfun/__printf_assert__.m,
scripts/testfun/__prog_output_assert__.m, scripts/testfun/__run_test_suite__.m,
scripts/time/clock.m, scripts/time/datenum.m, scripts/ui/errordlg.m,
scripts/ui/private/message_dialog.m: End m-files with 1 blank line.
author | Rik <rik@octave.org> |
---|---|
date | Wed, 28 Aug 2013 08:33:02 -0700 |
parents | 088d014a7fe2 |
children | 7bbe3658c5ef 446c46af4b42 |
line wrap: on
line source
## Copyright (C) 2009-2013 Eric Chassande-Mottin, CNRS (France) ## ## This file is part of Octave. ## ## Octave is free software; you can redistribute it and/or modify it ## under the terms of the GNU General Public License as published by ## the Free Software Foundation; either version 3 of the License, or (at ## your option) any later version. ## ## Octave is distributed in the hope that it will be useful, but ## WITHOUT ANY WARRANTY; without even the implied warranty of ## MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU ## General Public License for more details. ## ## You should have received a copy of the GNU General Public License ## along with Octave; see the file COPYING. If not, see ## <http://www.gnu.org/licenses/>. ## -*- texinfo -*- ## @deftypefn {Function File} {[@var{a}, @dots{}] =} textread (@var{filename}) ## @deftypefnx {Function File} {[@var{a}, @dots{}] =} textread (@var{filename}, @var{format}) ## @deftypefnx {Function File} {[@var{a}, @dots{}] =} textread (@var{filename}, @var{format}, @var{n}) ## @deftypefnx {Function File} {[@var{a}, @dots{}] =} textread (@var{filename}, @var{format}, @var{prop1}, @var{value1}, @dots{}) ## @deftypefnx {Function File} {[@var{a}, @dots{}] =} textread (@var{filename}, @var{format}, @var{n}, @var{prop1}, @var{value1}, @dots{}) ## Read data from a text file. ## ## The file @var{filename} is read and parsed according to @var{format}. The ## function behaves like @code{strread} except it works by parsing a file ## instead of a string. See the documentation of @code{strread} for details. ## ## In addition to the options supported by @code{strread}, this function ## supports two more: ## ## @itemize ## @item @qcode{"headerlines"}: ## The first @var{value} number of lines of @var{filename} are skipped. ## ## @item @qcode{"endofline"}: ## Specify a single character or @qcode{"\r\n"}. If no value is given, it ## will be inferred from the file. If set to "" (empty string) EOLs are ## ignored as delimiters. ## @end itemize ## ## The optional input @var{n} specifies the number of data lines to read; in ## this sense it differs slightly from the format repeat count in strread. ## ## If the format string is empty (not: omitted) and the file contains only ## numeric data (excluding headerlines), textread will return a rectangular ## matrix with the number of columns matching the number of numeric fields on ## the first data line of the file. Empty fields are returned as zero values. ## ## @seealso{strread, load, dlmread, fscanf, textscan} ## @end deftypefn function varargout = textread (filename, format = "%f", varargin) BUFLENGTH = 4096; # Read buffer to speed up processing @var{n} ## Check input if (nargin < 1) print_usage (); endif if (! ischar (filename) || ! ischar (format)) error ("textread: FILENAME and FORMAT arguments must be strings"); endif if (! isempty (varargin) && isnumeric (varargin{1})) nlines = varargin{1}; else nlines = Inf; endif if (nlines < 1) printf ("textread: N = 0, no data read\n"); varargout = cell (1, nargout); return; endif ## Read file fid = fopen (filename, "r"); if (fid == -1) error ("textread: could not open '%s' for reading", filename); endif ## Skip header lines if requested headerlines = find (strcmpi (varargin, "headerlines"), 1); if (! isempty (headerlines)) ## Beware of missing or wrong headerline value if (headerlines == numel (varargin) || ! isnumeric (varargin{headerlines + 1})) error ("missing or illegal value for 'headerlines'" ); endif ## Avoid conveying floats to fskipl varargin{headerlines + 1} = round (varargin{headerlines + 1}); ## Beware of zero valued headerline, fskipl would skip to EOF if (varargin{headerlines + 1} > 0) fskipl (fid, varargin{headerlines + 1}); varargin(headerlines:headerlines+1) = []; nargin = nargin - 2; elseif (varargin{headerlines + 1} < 0) warning ("textread: negative headerline value ignored"); endif endif st_pos = ftell (fid); ## Read a first file chunk. Rest follows after endofline processing [str, count] = fscanf (fid, "%c", BUFLENGTH); if (isempty (str) || count < 1) warning ("textread: empty file"); varargout = cell (1, nargout); return; endif endofline = find (strcmpi (varargin, "endofline"), 1); if (! isempty (endofline)) ## 'endofline' option set by user. if (! ischar (varargin{endofline + 1})); error ("character value required for EndOfLine"); endif else ## Determine EOL from file. Search for EOL candidates in first BUFLENGTH chars eol_srch_len = min (length (str), BUFLENGTH); ## First try DOS (CRLF) if (! isempty (strfind (str(1 : eol_srch_len), "\r\n"))) eol_char = "\r\n"; ## Perhaps old Macintosh? (CR) elseif (! isempty (strfind (str(1 : eol_srch_len), "\r"))) eol_char = "\r"; ## Otherwise, use plain *nix (LF) else eol_char = "\n"; endif ## Set up default endofline param value varargin(end+1:end+2) = {"endofline", eol_char}; endif ## Now that we know what EOL looks like, we can process format_repeat_count. ## FIXME The below isn't ML-compatible: counts lines, not format string uses if (isfinite (nlines) && (nlines > 0)) l_eol_char = length (eol_char); eoi = findstr (str, eol_char); n_eoi = length (eoi); nblks = 0; ## Avoid slow repeated str concatenation, first seek requested end of data while (n_eoi < nlines && count == BUFLENGTH) [nstr, count] = fscanf (fid, "%c", BUFLENGTH); if (count > 0) ## Watch out for multichar EOL being missed across buffer boundaries if (l_eol_char > 1) str = [str(end - length (eol_char) + 2 : end) nstr]; else str = nstr; endif eoi = findstr (str, eol_char); n_eoi += numel (eoi); ++nblks; endif endwhile ## Found EOL delimiting last requested line. Compute ptr (incl. EOL) if (isempty (eoi)) printf ("textread: format repeat count specified but no endofline found\n"); eoi_pos = nblks * BUFLENGTH + count; else eoi_pos = (nblks * BUFLENGTH) + eoi(end + min (nlines, n_eoi) - n_eoi); endif fseek (fid, st_pos, "bof"); str = fscanf (fid, "%c", eoi_pos); else fseek (fid, st_pos, "bof"); str = fread (fid, "char=>char").'; endif fclose (fid); ## Set up default whitespace param value if needed if (isempty (find (strcmpi ("whitespace", varargin)))) varargin(end+1:end+2) = {"whitespace", " \b\t"}; endif ## Call strread to make it do the real work [varargout{1:max (nargout, 1)}] = strread (str, format, varargin {:}); ## Hack to concatenate/reshape numeric output into 2D array (undocumented ML) ## In ML this only works in case of an empty format string if (isempty (format)) ## Get number of fields per line. ## 1. Get eol_char position iwhsp = find (strcmpi ("whitespace", varargin)); whsp = varargin{iwhsp + 1}; idx = regexp (str, eol_char, "once"); ## 2. Get first data line til EOL. Avoid corner case of just one line if (! isempty (idx)) str = str(1:idx-1); endif idelimiter = find (strcmpi (varargin, "delimiter"), 1); if (isempty (idelimiter)) ## Assume delimiter = whitespace ## 3A. whitespace incl. consecutive whitespace => single space str = regexprep (str, sprintf ("[%s]+", whsp), ' '); ## 4A. Remove possible leading & trailing spaces str = strtrim (str); ## 5A. Count spaces, add one to get nr of data fields per line ncols = numel (strfind (str, " ")) + 1; else ## 3B. Just count delimiters. FIXME: delimiters could occur in literals delimiter = varargin {idelimiter+1}; ncols = numel (regexp (str, sprintf ("[%s]", delimiter))) + 1; endif ## 6. Reshape; watch out, we need a transpose nrows = ceil (numel (varargout{1}) / ncols); pad = mod (numel (varargout{1}), ncols); if (pad > 0) pad = ncols - pad; varargout{1}(end+1 : end+pad) = NaN; endif varargout{1} = reshape (varargout{1}, ncols, nrows)'; ## ML replaces empty values with NaNs varargout{1}(find (isnan (varargout{1}))) = 0; endif endfunction %!test %! f = tmpnam (); %! d = rand (5, 3); %! dlmwrite (f, d, "precision", "%5.2f"); %! [a, b, c] = textread (f, "%f %f %f", "delimiter", ",", "headerlines", 3); %! unlink (f); %! assert (a, d(4:5, 1), 1e-2); %! assert (b, d(4:5, 2), 1e-2); %! assert (c, d(4:5, 3), 1e-2); %!test %! f = tmpnam (); %! d = rand (7, 2); %! dlmwrite (f, d, "precision", "%5.2f"); %! [a, b] = textread (f, "%f, %f", "headerlines", 1); %! unlink (f); %! assert (a, d(2:7, 1), 1e-2); %% Test reading 2D matrix with empty format %!test %! f = tmpnam (); %! d = rand (5, 2); %! dlmwrite (f, d, "precision", "%5.2f"); %! A = textread (f, "", "headerlines", 3); %! unlink (f); %! assert (A, d(4:5, :), 1e-2); %% Read multiple lines using empty format string %!test %! f = tmpnam (); %! unlink (f); %! fid = fopen (f, "w"); %! d = rand (1, 4); %! fprintf (fid, " %f %f %f %f ", d); %! fclose (fid); %! A = textread (f, ""); %! unlink (f); %! assert (A, d, 1e-6); %% Empty format, corner case = one line w/o EOL %!test %! f = tmpnam (); %! unlink (f); %! fid = fopen (f, "w"); %! d = rand (1, 4); %! fprintf (fid, " %f %f %f %f ", d); %! fclose (fid); %! A = textread (f, ""); %! unlink (f); %! assert (A, d, 1e-6); %% Read multiple lines using empty format string, missing data (should be 0) %!test %! f = tmpnam (); %! unlink (f); %! fid = fopen (f, "w"); %! d = rand (1, 4); %! fprintf (fid, "%f, %f, , %f, %f ", d); %! fclose (fid); %! A = textread (f, ""); %! unlink (f); %! assert (A, [ d(1:2) 0 d(3:4)], 1e-6); %% Test with empty positions - ML returns 0 for empty fields %!test %! f = tmpnam (); %! unlink (f); %! fid = fopen (f, "w"); %! d = rand (1, 4); %! fprintf (fid, ",2,,4\n5,,7,\n"); %! fclose (fid); %! A = textread (f, "", "delimiter", ","); %! unlink (f); %! assert (A, [0 2 0 4; 5 0 7 0], 1e-6); %% Another test with empty format + positions, now with more incomplete lower %% row (must be appended with zeros to get rectangular matrix) %!test %! f = tmpnam (); %! unlink (f); %! fid = fopen (f, "w"); %! d = rand (1, 4); %! fprintf (fid, ",2,,4\n5,\n"); %! fclose (fid); %! A = textread (f, "", "delimiter", ","); %! unlink (f); %! assert (A, [0 2 0 4; 5 0 0 0], 1e-6); %% Test input validation %!error textread () %!error textread (1) %!error <arguments must be strings> textread (1, "%f") %!error <arguments must be strings> textread ("fname", 1) %!error <missing or illegal value for> textread (file_in_loadpath ("textread.m"), "", "headerlines") %!error <missing or illegal value for> textread (file_in_loadpath ("textread.m"), "", "headerlines", 'hh') %!error <character value required for> textread (file_in_loadpath ("textread.m"), "%s", "endofline", true)